Carnegie Mellon University researchers have joined a five-year, $10 million initiative funded by the National Science Foundation to study using computer science to develop tools for studying how people interact.

The Computational Behavioral Science Project is expected to aid in evaluating social interactions and other behaviors that can be used in diagnosing or treating behavioral disorders such as autism. Part of the Expeditions in Computing program of the NSF's Directorate for Computer & Information Science & Engineering, it includes researchers from the University of Illinois at Urbana-Champaign, the University of Southern California and the Massachusetts Institute of Technology, with the Georgia Institute of Technology serving as the lead institution.

Computer vision and machine learning programs are two areas of study expected to add to the understanding of children's behavior, including determining early signs of autism, according to Anind Dey, associate professor in Carnegie Mellon's Human-Computer Interaction Institute.

An expert in computer vision, Takeo Kanade, Carnegie Mellon professor of robotics and computer science, will lead work to analyze videos, amateur or otherwise, for early signs of autistic behavior, such as the rocking, clapping and other repetitive stereotypical behaviors known as "stimming." Other body behaviors could also be studied.

Looking for more from the Post-Gazette? Join PG+, our members-only web site. You'll get exclusive sports content, opinion, financial information, discounts from retailers and restaurants, and more. Our introduction to PG+ gives you all the details.